Olmo 3 — Ai2 (Allen Institute for AI) 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
完全开放，而不只是开放权重：Ai2以Apache-2.0许可公开权重、训练数据（Dolma 3）、代码和中间检查点。每个尺寸都提供Base、Instruct和Think三种变体，因此当训练过程本身必须可审计时，应当首选这个系列。
变体
Olmo 3 最小的变体在 Q4_K_M 下约需 5 GB 显存——量化权重加框架开销，不含 KV 缓存。
| 模型 | Q4 下显存 | 显存 | 上下文 | 运行 |
|---|---|---|---|---|
| Olmo 3 7B → 7B | ~5 GB | 65,536 | ollama run olmo-3 | |
| Olmo 3 32B → 32B | ~20.1 GB | 65,536 | ollama run olmo-3 |
显存为 Q4_K_M 下的量化权重加开销，与 GPU 与显存检测器使用同一引擎计算。
如何在本地运行 Olmo 3
安装 Ollama，然后拉取标签。
ollama run olmo-3在上方选择一个尺寸，查看它自己的显存、速度估算和安装命令。
许可证
Commercial use permitted. No usage restrictions beyond attribution.
适用于: Olmo 3 7B, Olmo 3 32B推荐 GPU
目录中能在本地运行 Olmo 3（至少 5 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Olmo 3 — 常见问题
How much VRAM does Olmo 3 need?
Olmo 3 needs about 5 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Olmo 3 7B (5 GB, Q4_K_M); Olmo 3 32B (20 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Olmo 3 on an RTX 4090 (24 GB)?
Yes — Olmo 3 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Olmo 3?
Q4_K_M is the best balance of quality and VRAM for Olmo 3 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Olmo 3 with Ollama?
Olmo 3 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.